memory-extractor

memory-extractor is an agent for Claude Code from parcadei/Continuous-Claude-v3. It costs 16 tokens per session (1,422 once invoked), scanned A, original, MIT.

An agent that finds changes in understanding—such as realizations, corrections, and unexpected insights—in Claude Code session transcripts. It stores these findings as learnings.

In plain words
What is it for?
Reading session JSONL files, filtering thinking blocks for perception signals, checking extraction statistics, and recording useful insights from coding sessions.
Why use it?
Important lessons in a long coding session can be difficult to recover later. This separates meaningful shifts in understanding from ordinary transcript content.

Agent for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/parcadei/continuous-claude-v3/memory-extractor
Clone the repo
git clone --depth 1 https://github.com/parcadei/Continuous-Claude-v3

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for memory-extractor

README.md
[![agentmods](https://agentmods.dev/badge/agents/parcadei/continuous-claude-v3/memory-extractor.svg)](https://agentmods.dev/agents/parcadei/continuous-claude-v3/memory-extractor)
Your own site
<a href="https://agentmods.dev/agents/parcadei/continuous-claude-v3/memory-extractor"><img src="https://agentmods.dev/badge/agents/parcadei/continuous-claude-v3/memory-extractor.svg" alt="Measured on agentmods" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,422 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00016 $0.01422
Opus 5 $0.00008 $0.00711
Sonnet 5 $0.00003 $0.00284
Haiku 4.5 $0.00002 $0.00142

Measured 4d ago against content hash 996e6a1429d9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

memory-extractor scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/agents/memory-extractor.md · 176 lines

How it starts

The opening of the file, as written. The whole thing — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Memory Extractor Agent

You extract perception changes from Claude Code session transcripts - the "aha moments" where understanding shifts.

Philosophy

"A point of view is worth 80 IQ points" - Alan Kay

We're looking for mental model shifts, not just error→fix pairs:

  • Realizations: "Oh, X was actually Y"
  • Corrections: "I was wrong about..."
  • Insights: "The pattern here is..."
  • Surprises: "Unexpected that..."

Input

You receive:

  • JSONL_PATH: Path to session JSONL file
  • SESSION_ID: Session identifier (optional, extracted from path if not provided)

Process

Step 1: Extract Thinking Blocks with Perception Signals

# Use the extraction script with filtering
(cd $CLAUDE_PROJECT_DIR/opc && uv run python scripts/core/extract_thinking_blocks.py \
  --jsonl "$JSONL_PATH" \
  --filter \
  --format json) > /tmp/perception-blocks.json

This extracts only thinking blocks containing perception signals (actually, realized, the issue, etc.).

Step 2: Check Stats

(cd $CLAUDE_PROJECT_DIR/opc && uv run python scripts/core/extract_thinking_blocks.py \
  --jsonl "$JSONL_PATH" \
  --stats)

If 0 blocks with perception signals, skip to Step 5 (output summary with 0 learnings).

Step 3: Classify Perception Changes

Read the extracted blocks from /tmp/perception-blocks.json and classify each one:

Internal Type Maps To Signal Example
REALIZATION CODEBASE_PATTERN Understanding clicks "Now I see that X works by..."
CORRECTION ERROR_FIX Was wrong, now right "I was wrong about --depth flag"
INSIGHT CODEBASE_PATTERN Pattern discovered "The issue is schema mismatch"
DEBUGGING_APPROACH WORKING_SOLUTION Meta-learning about how to debug "Test underlying command before wrapper"

Valid store_learning.py types:

  • FAILED_APPROACH - Things that didn't work
  • WORKING_SOLUTION - Successful approaches
  • USER_PREFERENCE - User style/preferences
  • CODEBASE_PATTERN - Discovered code patterns
  • ARCHITECTURAL_DECISION - Design choices made
  • ERROR_FIX - Error→solution pairs
  • OPEN_THREAD - Unfinished work/TODOs

Read the full file on GitHub · 176 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago First seen · 176 lines · 16 tokens per session scan A 996e6a1429d9

Subscribe to this mod's changes

memory-extractor is an agent published in the GitHub repository parcadei/Continuous-Claude-v3 (3,934 stars, last pushed 7mo ago), licensed MIT. It adds 16 tokens to every session and 1,422 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other agents, from other repositories

fizzy-tasks

Lightweight agent for Fizzy.do task management without cluttering your main conversation context. Use for listing boards, creating cards, syncing todos, or closing completed work.

keskinonur/claude-plugin-fizzy · 39 tokens

ralph-e2e-verifier

Use this agent when you need to run the Ralph orchestrator end-to-end test suite, analyze diagnostic outputs, and generate comprehensive reports of findings. This includes validating backend connectivity, orchestration loop behavior, event parsing, hat collections, memory systems, and error handling. Invoke this agent…

mikeyobrien/ralph-orchestrator · 358 tokens

immune-scan

You are an adaptive immune system scanner. You detect known error patterns (antibodies) and discover new threats in any content. You also identify effective strategies (positive patterns) worth remembering. You are precise, concise, and limit your output strictly to the JSON object.

Mnemoclaw/immune · 3 tokens

knowledge-primer

Walks the beds before work begins and reports what is already known. Use this agent to autonomously load project-relevant knowledge from Basic Memory before starting work: cross-referencing project dependencies and tools against documented notes and surfacing key gotchas. Typical triggers include: "prime the knowledge…

voxpelli/vp-claude · 131 tokens

fec-performance-optimizer

Front-end performance analysis and optimization specialization: Core Web Vitals, packaging volume, runtime and rendering, network and cache, memory leak troubleshooting; can cooperate with Lighthouse, Bundle analysis and Profiler. Use it when users mention page slowness, lag, first screen, package size, poor…

bovinphang/frontend-craft · 0 tokens

vault-writer

You are a note creation agent for a personal Zettelkasten vault in Obsidian.

tuan3w/obsidian-vault-agent · 3 tokens